Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2187 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.8872. Min Act: -0.0001
Data Index: 1053586 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.6634. Min Act: -0.0001
Data Index: 680604 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.5235. Min Act: -0.0001
Data Index: 348653 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.4508. Min Act: -0.0001
Data Index: 239856 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.2984. Min Act: -0.0001
Data Index: 443430 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.2960. Min Act: -0.0001
Data Index: 893029 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.2190. Min Act: -0.0001
Data Index: 719769 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.3240. Min Act: -0.0001
Data Index: 401561 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.3048. Min Act: -0.0001
Data Index: 1116383 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.2283. Min Act: -0.0001
Data Index: 1200337 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.3679. Min Act: -0.0001
Data Index: 170807 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1792. Min Act: -0.0001
Data Index: 718836 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1855. Min Act: -0.0001
Data Index: 886088 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1791. Min Act: -0.0001
Data Index: 196896 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1894. Min Act: -0.0001
Data Index: 572065 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1986. Min Act: -0.0001
Data Index: 466622 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1023. Min Act: -0.0001
Data Index: 1173554 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1528. Min Act: -0.0001
Data Index: 815432 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.1131. Min Act: -0.0001
Data Index: 140874 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8872. Min Range: -1.8872
Max Act: 1.2125. Min Act: -0.0001
Data Index: 344651 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19